CN112699245A - Construction method and device and application method and device of budget management knowledge graph - Google Patents
Construction method and device and application method and device of budget management knowledge graph Download PDFInfo
- Publication number
- CN112699245A CN112699245A CN201910993811.9A CN201910993811A CN112699245A CN 112699245 A CN112699245 A CN 112699245A CN 201910993811 A CN201910993811 A CN 201910993811A CN 112699245 A CN112699245 A CN 112699245A
- Authority
- CN
- China
- Prior art keywords
- budget
- entity
- entities
- knowledge graph
- knowledge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000010276 construction Methods 0.000 title claims abstract description 18
- 230000008520 organization Effects 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims description 24
- 238000004458 analytical method Methods 0.000 claims description 9
- 230000001960 triggered effect Effects 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 238000007726 management method Methods 0.000 description 70
- 238000010586 diagram Methods 0.000 description 11
- 238000004519 manufacturing process Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 7
- 238000011084 recovery Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 6
- 239000013598 vector Substances 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000002347 injection Methods 0.000 description 4
- 239000007924 injection Substances 0.000 description 4
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 4
- 238000007689 inspection Methods 0.000 description 3
- 238000005086 pumping Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000003345 natural gas Substances 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000012015 optical character recognition Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/12—Accounting
- G06Q40/125—Finance or payroll
Abstract
The invention discloses a construction method and a device of a budget management knowledge graph, an application method and a device, relating to the technical field of budget management, wherein the budget management is optimized by using the knowledge graph, and various financial and business data of a query unit can be rapidly and comprehensively acquired as much as possible by retrieving the budget management knowledge graph, and the main technical scheme of the invention is as follows: acquiring historical budget data; extracting ontology information from the historical budget data, wherein the ontology information at least comprises: a plurality of entity categories and associated relationships existing between entities respectively corresponding to different entity categories, wherein the entity categories are at least: organization class, budget items class, asset class, service class, contract class; and constructing a budget management knowledge graph according to the association relationship existing between the entities respectively corresponding to the different entity types. The invention is applied to optimizing budget management.
Description
Technical Field
The invention relates to the technical field of budget management, in particular to a construction method and device and an application method and device of a budget management knowledge graph.
Background
Budget management means that an enterprise fully and comprehensively predicts and plans future business activities and corresponding financial results under the guidance of a strategic target, and continuously compares and analyzes actual completion conditions with the budget target through monitoring an execution process, so that improvement and adjustment of the business activities are guided in time, and managers are helped to manage the enterprise more effectively and achieve the strategic target to the maximum extent.
At present, when enterprises face huge performance pressure, budgeting in the current way has to face the following inconveniences: (1) the budget targets based on historical data are played between the upper level and the lower level, and the budget targets lack objectivity due to excessive human interference; (2) due to the consideration of short-term profit, enterprises can terminate some long-term and large-amount expenditure projects, so that the budget items are lack of continuity; (3) the lower level unit deals with the great reduction of the upper level unit by adding budget items or increasing expenditure amount, and the budget items are lack of reality in the past; (4) the upper level unit "reduce for decrease" compresses the budget expenditure making the budget objective less reasonable.
The main reason for the above-mentioned trouble lies in that the information and data are not fully utilized, shared and communicated, and especially, when the management level or range of the enterprise is relatively large, the utilization rate of the information of the upper layer or front end to the lower layer or back end is lower, because they cannot timely and efficiently acquire the data, and only the budget and amount can be confirmed by experience.
Disclosure of Invention
In view of the above, the present invention provides a construction method and apparatus, and an application method and apparatus of a budget management knowledge graph, and mainly aims to optimize budget management by using the knowledge graph, and by retrieving the budget management knowledge graph, various financial and business data of an inquiry unit can be quickly and comprehensively acquired as much as possible, which is helpful to provide an efficient implementation manner for planning a budget scheme, and judging authenticity and rationality of budget items or budget targets.
In order to achieve the above purpose, the present invention mainly provides the following technical solutions:
in a first aspect, the present invention provides a method for constructing a budget management knowledge graph, including:
acquiring historical budget data;
extracting ontology information from the historical budget data, wherein the ontology information at least comprises: a plurality of entity categories and associated relationships existing between entities respectively corresponding to different entity categories, wherein the entity categories are at least: organization class, budget items class, asset class, service class, contract class;
and constructing a budget management knowledge graph according to the association relationship existing between the entities respectively corresponding to the different entity types.
Optionally, the extracting ontology information from the historical budget data includes:
analyzing knowledge element information contained in the historical budget data, wherein the knowledge element information comprises entities, relations among the entities, attributes of the entities and attribute values of the attributes;
constructing a knowledge triple according to the knowledge element information;
classifying the plurality of entities according to a preset classification rule to obtain an entity corresponding to each category;
searching whether any two entities have an association relation between different categories;
if so, acquiring the association relation;
and adding the association relation between the knowledge triple and the found any two entities into the body information.
Optionally, after the analyzing knowledge element information included in the historical budget data, the method further includes:
processing the entity contained in the knowledge element information by utilizing entity disambiguation; and/or the presence of a gas in the gas,
and processing the entity contained in the knowledge element information by utilizing coreference resolution.
Optionally, after the constructing a knowledge triple according to the knowledge element information, the method further includes:
judging whether the similarity between the two triples reaches a preset threshold value or not by calculating word similarity;
and if so, executing deduplication processing on the two triples.
In a second aspect, the present invention further provides an application method of a budget management knowledge-graph, which is used for the budget management knowledge-graph obtained by the above construction method of a budget management knowledge-graph, and the method includes:
when a triggered retrieval instruction is received, the budget management knowledge graph is used as a bottom retrieval support, and a retrieval result corresponding to the retrieval instruction is output;
comparing the retrieval result with a white list corresponding to different service scenes;
and if the data are not matched, outputting alarm information.
In a third aspect, the present invention further provides a device for constructing a budget management knowledge base, where the device includes:
the acquisition unit is used for acquiring historical budget data;
an extracting unit, configured to extract ontology information from the historical budget data acquired by the acquiring unit, where the ontology information at least includes: a plurality of entity categories and associated relationships existing between entities respectively corresponding to different entity categories, wherein the entity categories are at least: organization class, budget items class, asset class, service class, contract class;
and the construction unit is used for constructing the budget management knowledge graph according to the association relation existing between the entities which are extracted by the extraction unit and respectively correspond to different entity types.
Optionally, the extracting unit includes:
the analysis module is used for analyzing knowledge element information contained in the historical budget data, wherein the knowledge element information contains entities, relations among the entities, attributes of the entities and attribute values of the attributes;
the construction module is used for constructing a knowledge triple according to the knowledge element information obtained by the analysis module;
the classification module is used for classifying the entities obtained by the analysis modules according to a preset classification rule to obtain an entity corresponding to each category;
the searching module is used for searching whether any two entities have an association relation between different categories;
the obtaining module is used for obtaining the incidence relation if the searching module finds that any two entities have the incidence relation;
and the adding module is used for adding the knowledge triple constructed by the constructing module and the incidence relation of any two entities acquired by the acquiring module into the body information.
Optionally, the extracting unit further includes:
a processing module, configured to process an entity included in the knowledge element information by using entity disambiguation after analyzing the knowledge element information included in the historical budget data;
and the processing module is also used for processing the entity contained in the knowledge element information by utilizing coreference resolution.
Optionally, the extracting unit further includes:
the judging module is used for judging whether the similarity between the two triples reaches a preset threshold value or not by calculating word similarity after the knowledge triples are constructed according to the knowledge element information;
the processing module is further configured to perform deduplication processing on the two triples when the determining module determines whether the similarity between the two triples reaches a preset threshold.
In a fourth aspect, the present invention further provides an apparatus for applying a budget management knowledge base, where the method includes:
the retrieval unit is used for taking the budget management knowledge graph as bottom retrieval support when receiving a triggered retrieval instruction;
the output unit is used for outputting a retrieval result corresponding to the retrieval instruction;
the comparison unit is used for comparing the retrieval result output by the output unit with the white lists corresponding to different service scenes;
and the output unit is also used for outputting alarm information when the comparison unit determines that the retrieval result is not matched with the white lists corresponding to different service scenes.
In still another aspect, the present invention further provides a storage medium, where the storage medium includes a stored program, where the apparatus on which the storage medium is located is controlled to execute the method for constructing a budget management knowledge graph as described above when the program runs;
alternatively, the application method of the budget management knowledge graph as described above is performed.
In yet another aspect, the present invention also provides an electronic device comprising at least one processor, and at least one memory, a bus connected to the processor;
the processor and the memory complete mutual communication through the bus;
the processor is used for calling program instructions in the memory to execute the construction method of the budget management knowledge graph;
alternatively, the application method of the budget management knowledge graph as described above is performed.
By the technical scheme, the technical scheme provided by the invention at least has the following advantages:
the invention provides a construction method and a device of a budget management knowledge graph, and an application method and a device thereof, wherein the invention utilizes historical budget data to construct the budget management knowledge graph comprising entity categories such as organization categories, budget items categories, asset categories, service categories, combination categories and the like, and can quickly and comprehensively acquire various financial and service data of a query unit as much as possible by retrieving the budget management knowledge graph, thereby being beneficial to providing an efficient implementation mode for the planning of a budget scheme, judging the authenticity and reasonability of budget items or budget targets. Compared with the prior art, the method solves the problem that the budget planning in the existing mode cannot be fully and effectively utilized and the intercommunication information and data are shared, so that a plurality of troubles are brought.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flowchart of a method for constructing a budget management knowledge graph according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating an example of a display of an embodiment of the present invention with associations between entities of different classes intercepted;
FIG. 3 is a diagram illustrating exemplary attributes associated with a generic entity class according to an embodiment of the present invention;
FIG. 4 is a flowchart of another method for constructing a budget management knowledge graph according to an embodiment of the present invention;
FIG. 5 is a flowchart of an application method of a budget management knowledge graph according to an embodiment of the present invention;
FIG. 6 is a block diagram of an apparatus for constructing a budget management knowledge-graph according to an embodiment of the present invention;
FIG. 7 is a block diagram of an alternative apparatus for constructing a budget management knowledge-graph according to an embodiment of the present invention;
FIG. 8 is a block diagram of an application apparatus for budget management knowledge-graph according to an embodiment of the present invention;
fig. 9 is an electronic device according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The embodiment of the invention provides a method for constructing a budget management knowledge graph, which is to construct a budget management knowledge graph comprising entity categories such as organization categories, budget items categories, asset categories, service categories and similar categories by utilizing historical budget data, and comprises the following specific steps of:
101. and acquiring historical budget data.
In the embodiment of the present invention, the obtained historical budget data is equivalent to a data source for collecting data used for constructing a knowledge graph, and a specific method for obtaining the historical budget data may be as follows:
structured data is extracted from budget databases, financial accounting databases and other related databases through a data interface. Alternatively, the semi-structured data and the unstructured data in the paper document are recognized and obtained by an Optical Character Recognition (OCR) technology, such as: budget responsibility, budget adjustment notice, etc.
102. And extracting the body information from the historical budget data.
Wherein, the body information at least includes: the entity types and the entity corresponding to different entity types have incidence relation, the entity types are at least: organization class, budget items class, assets class, business class, contract class.
Specifically, the detailed explanation of the plurality of entity categories is: the organization entity takes each budget responsibility (performance) center of an enterprise as an ontology and comprises attribute names such as responsibility center types and assessment indexes, namely, the organization entity describes specific attributes of each responsibility center; the budget item entity is a description of specific items considered in budgeting, and comprises attributes and data such as name, budget amount, whether long-term items, actual occurrence amount, declaration amount, approval amount and service workload; the asset entity is mainly information of various assets used in the production and operation process of an enterprise, and comprises information such as names, using units, installation positions, original values, net values, service lives and the like; the service entity refers to information of each service specifically developed in budget responsibility, such as service name and type; the contract entity is information related to the parties or the agreement between the parties for setting up, changing and terminating the civil relationship.
For example, in order to meet the operation requirement of the oil mine enterprise, an organization entity, a budget item entity, an asset entity, a business entity, and a contract entity are listed as follows:
organization class entity: company a, oil production plant B, oil recovery fleet D, etc.
Budget items class entity: cost of labor, labor of purchase, tubing procurement, etc.
Asset class entity: pumping wells, flooding wells, flowing wells, and the like.
And (3) a service class entity: oil recovery operations, flooding injection, natural gas compression, and the like.
Contract type entity: compliance with safety work terms, labor protection terms, employment terms, and the like.
Further, referring to fig. 2, the association relationship existing between different types of entities is partially intercepted, and the following examples are given:
between the organization entities, "company a, production plant B, production plant C, and production crew D", there is a hierarchical relationship between the entities according to the arrows in fig. 2.
The budget items entity ' labor cost expenditure, purchasing labor expenditure and oil pipe purchasing expenditure ' is compiled by the oil production team D, so that the compilation relation exists between the budget items entity ' oil production team D ' and the budget items entity ' respectively.
The asset entity 'pumping well, water injection well and self-injection well' belongs to an oil recovery team D, so that the asset entity 'oil recovery team D' has a relationship with the asset entity 'oil recovery team D';
the business entity ' oil extraction operation, oil displacement injection and natural gas compression ' is a business developed by an ' oil recovery team ' D, so that business development relations exist between the business entity ' oil recovery team D ' and the business entity ' respectively.
It should be noted that, according to business requirements, an association relationship may be established between any two of the entity categories shown in fig. 2, except for the association relationship already shown in fig. 2, such as: the asset entity "pumping well" is used for oil production operation, so that an association relationship can be established with the business entity "oil production operation", such as: the service entity "oil production operation" is labor-consuming, so that an association relationship can be established with the budget item entity "labor cost expenditure", etc., so as to avoid the connecting lines illustrated in fig. 2 being messy and unclear, which is not exemplified here.
103. And constructing a budget management knowledge graph according to the incidence relation existing between the entities respectively corresponding to different entity types.
In the embodiment of the present invention, the ontology information at least includes entity categories as: organization class, budget items class, assets class, business class, contract class. Under an entity category, each entity is an entity or attribute having an association, so each entity is equivalent to a data set, which is described with reference to fig. 3, for simplicity of description, fig. 3 only illustrates several attributes corresponding to different entities indicated in a general way, but according to the illustration in fig. 3, each entity is equivalent to a data set by combining entities of different categories and their corresponding attributes.
In the embodiment of the invention, the association is established for the data sets corresponding to the entities of different categories according to the association relationship existing between the entities respectively corresponding to the different entity categories, so that the budget management knowledge graph comprising a plurality of data sets is obtained.
The embodiment of the invention provides a method for constructing a budget management knowledge graph, which is used for constructing the budget management knowledge graph comprising entity categories such as organization categories, budget items categories, asset categories, service categories, combination categories and the like by utilizing historical budget data, and can quickly acquire various financial and service data of a query unit by retrieving the budget management knowledge graph, thereby being beneficial to providing an efficient implementation mode for the compilation and verification of a budget scheme. Compared with the prior art, the method solves the problem that the budget planning in the existing mode cannot be fully and effectively utilized and the intercommunication information and data are shared, so that a plurality of troubles are brought.
In order to explain the above embodiments in more detail, the embodiment of the present invention further provides another method for constructing a budget management knowledge graph, as shown in fig. 4, which is a refinement and supplement to the above embodiments, and the following specific steps are provided for the embodiment of the present invention:
201. and acquiring historical budget data.
In the embodiment of the present invention, for the statement of this step, refer to step 101, and will not be described herein again.
202. And analyzing knowledge element information contained in the historical budget data, wherein the knowledge element information comprises entities, relations among the entities, attributes of the entities and attribute values of the attributes.
Further, after the plurality of entities are obtained through parsing, the entities are processed by entity disambiguation (entity unification), or the entities are processed by coreference resolution, specifically, the following statements are made:
in the embodiment of the present invention, the knowledge elements (i.e., ontology information such as entities, relationships, attributes, attribute values, etc.) may be extracted from the historical budget data by using technologies such as Named Entity identification (NER), Entity unification, coreference resolution, etc., for example, the specific steps may include the following:
first, for unstructured data and semi-structured data contained in historical budget data, processing methods that may include, but are not limited to, are: and identifying the data received in the data collection process according to set keywords, and further classifying and collecting the identified data into entity information, relationship information, attribute information and the like. For structured data contained in historical budget data, collecting field data may include, but is not limited to, further categorizing the field data into ontology information such as entities, relationships, attributes, and the like.
Secondly, adopt entity unification, coreference resolution to carry out operations such as duplicate removal, unification to the body information that collects again to realize entity alignment to reduce the redundancy of relevant information, avoid leading to appearing information interference when establishing the triple because of entity misalignment, specifically include as follows:
the main idea of entity unification (also called entity disambiguation) is to calculate the similarity between entities and judge whether the entities are possibly overlapped or not through the ranking of the similarity. A specific method, for example, a Vector Space Model (VSM), represents each entity as a low-dimensional dense Vector, and calculates the similarity distance by the cosine similarity of the vectors. As for how to represent an entity as a vector, the entity can be represented as a vector by using context information, description information, etc. of the entity, using word2vector, etc.
In the embodiment of the invention, the entity disambiguation technology is used for screening the knowledge elements obtained from the historical budget data, and the functions are as follows: entities with higher similarity are overlapped, because the expression of the language is various, but the entity diversity degree is too high, the entity diversity degree is unnecessary, the excessive processing cost caused by the excessive entity diversity degree is reduced, unnecessary redundant information is reduced due to the excessive creation of triples with higher similarity, and the efficiency of creating the triples is improved.
Furthermore, in historical budget data, pronouns, appellations and abbreviations are used to refer to the aforementioned full names of entities according to one's habits. For example, the beginning of the article may be written as "harbinge university", hereinafter may be referred to as "hakuang", "Gongda", etc., and also may be referred to as "this university", "her", etc., which are referred to as a co-reference phenomenon, but for a computer, how to merge different descriptions of the same entity in knowledge element information together, it is necessary to adopt a co-reference resolution technique, specifically including but not limited to constructing a high-precision natural language processing model, so as to improve the accuracy of analysis semantics, merge different descriptions of the same entity in historical budget data, so as to equivalently refine knowledge elements, ensure the quality of acquired knowledge elements, and finally improve the quality of constructing budget management knowledge maps. Meanwhile, by utilizing the coreference resolution technology, redundant information with low quality is reduced, and the efficiency of constructing the knowledge graph is improved.
In the embodiment of the invention, for entity disambiguation and coreference resolution, one or both of the entity disambiguation and coreference resolution can be selected, and the quality and the efficiency of constructing the knowledge graph are finally improved.
203. And constructing a knowledge triple according to the knowledge element information. The collected and processed data framework entity is used to fill in the related attributes and attribute values, so that the collected and processed data is formatted into triples.
For the embodiment of the present invention, the established triple may be further evaluated through sampling inspection/machine rule check, such as: and analyzing the semantics of the three words contained in the triples by utilizing a natural language processing technology so as to judge whether the words are correct or matched. Or, whether the similarity between the two triples reaches a preset threshold value can be judged by calculating the word similarity, if so, the duplicate removal processing is executed on the two triples, and the quality evaluation of the triples is indirectly realized. Or, a white list or a black list can be pre-established, so that the triple is matched with the white list or the black list, and the purpose of detecting the quality of the triple is achieved.
204. Classifying the entities according to a preset classification rule to obtain an entity corresponding to each category, searching whether any two entities have an association relationship between different categories, and if so, acquiring the association relationship.
The preset classification rule can be a category established according to different service requirements, so that the entity can be determined to which category the entity belongs by analyzing the similarity association between the semantics of the entity and the category. Furthermore, the mapping relationship between the semantics and the categories can be preset, so that after the analysis entity obtains the semantics, the matching can be directly completed according to the mapping relationship.
In the embodiment of the present invention, if an association relationship exists between two entities found between different categories, data sets corresponding to the different categories may be connected according to the association relationship, for example: as shown in fig. 2, there is a compilation relationship between the budget items entity "labor cost expenditure, purchasing labor expenditure, and oil pipe purchasing expenditure" and the organization entity "oil production team D", respectively. Since there may be an association relationship between different entities in the same category, and there may also be an association between an entity and an attribute, in this example, if it is found that there is an association between the entity "labor cost expenditure" and the entity "oil field crew D", then by using this association, the data set obtained with the entity "labor cost expenditure" can be associated with the data set obtained with the entity "oil field crew D", so as to obtain the sum of the two data sets.
205. And adding the association relation between the knowledge triples and any two searched entities into the body information.
The body information at least includes: the entity types and the entity corresponding to different entity types have incidence relation, the entity types are at least: organization class, budget items class, assets class, business class, contract class.
In the embodiment of the present invention, in addition to adding the constructed triple to the ontology information, the embodiment of the present invention establishes association between data sets corresponding to different entity categories according to the association relationship existing between the entities corresponding to the different entity categories, so as to obtain the budget management knowledge graph including a plurality of data sets. Therefore, to successfully construct the knowledge graph, it is also necessary to add such an association relationship to the ontology information.
206. And constructing a budget management knowledge graph according to the incidence relation existing between the entities respectively corresponding to different entity types.
In the embodiment of the invention, after the ontology information is obtained, the ontology information is stored in a data layer and a mode layer of the knowledge graph, namely, the ontology information is stored in a graph database (such as a Neo4j graph database) according to a certain format, so that on the basis of the constructed triples, the constructed triples are associated according to the association relationship existing between the entities respectively corresponding to different entity types, and the budget management knowledge graph is finally obtained.
It should be noted that, the budget management knowledge graph may also be updated according to the service requirement, and the update of the knowledge graph includes two contents: the first is data updating, which mainly refers to the change on the data layer, i.e. the updating of the stored content of the database, such as the operations of adding, deleting and changing entities and attribute values; and ontology updating, which mainly refers to updating on a mode layer, namely updating of a logic architecture of the knowledge graph, such as operations of adding, deleting and changing relationships and attributes. From the implementation point of view, the knowledge updating is consistent with the collection, processing and storage of data.
Further, an embodiment of the present invention further provides a method for applying a budget management knowledge graph, as shown in fig. 5, the method further provides a method for verifying retrieval information by using a white list corresponding to different service scenarios, so as to indirectly perform verification or quality inspection on an existing budget, and the following specific steps are provided for the embodiment of the present invention:
301. and when a triggered retrieval instruction is received, taking the budget management knowledge graph as a bottom retrieval support, and outputting a retrieval result corresponding to the retrieval instruction.
In the embodiment of the invention, the application of the knowledge graph after the construction comprises the rapid retrieval of data, so that the reality judgment of budget items, the reasonability judgment of budget targets, intelligent prediction and the like are realized according to the retrieved comprehensive data information, and an upper-layer application model or program is generally required to be developed in a customized manner according to requirements.
302. And comparing the retrieval result with the white lists corresponding to different service scenes.
303. And if the white lists corresponding to different service scenes are not matched, outputting alarm information.
In the embodiment of the present invention, for the above steps 301-302, a white list may be set in advance according to different service scenarios, for example: for the downhole operation, a reasonable range value of the lighting electricity utilization degree is preset, and if the budget lighting electricity utilization degree in the retrieval result exceeds the range, the budget is unreasonable. In the embodiment of the present invention, the purpose of setting the white list is: as the basis for judging the authenticity judgment of budget planning, the target reasonability judgment and the intelligent prediction, the early warning information can be correspondingly added into the blacklist, so that the white list and the blacklist are utilized for assisting the work.
Further, as an implementation of the methods shown in fig. 1 and fig. 4, an embodiment of the present invention provides a device for constructing a budget management knowledge graph. The embodiment of the apparatus corresponds to the embodiment of the method, and for convenience of reading, details in the embodiment of the apparatus are not repeated one by one, but it should be clear that the apparatus in the embodiment can correspondingly implement all the contents in the embodiment of the method. The apparatus is applied to optimize budget management by using knowledge graph, and specifically as shown in fig. 6, the apparatus includes:
an acquisition unit 31 configured to acquire historical budget data;
an extracting unit 32, configured to extract ontology information from the historical budget data acquired by the acquiring unit 31, where the ontology information at least includes: a plurality of entity categories and associated relationships existing between entities respectively corresponding to different entity categories, wherein the entity categories are at least: organization class, budget items class, asset class, service class, contract class;
the construction unit 33 constructs the budget management knowledge graph according to the association relationship between the entities corresponding to the different entity categories extracted by the extraction unit 32.
Further, as shown in fig. 7, the extracting unit 32 includes:
an analyzing module 321, configured to analyze knowledge element information included in the historical budget data, where the knowledge element information includes entities, relationships among the entities, attributes of the entities, and attribute values of the attributes;
a constructing module 322, configured to construct a knowledge triple according to the knowledge element information obtained by the analyzing module 321;
a classification module 323, configured to classify, according to a preset classification rule, the entities obtained by the multiple analysis modules 321, so as to obtain an entity corresponding to each category;
a searching module 324, configured to search, between different categories, whether an association relationship exists between any two entities;
an obtaining module 325, configured to obtain the association relationship if the searching module 324 finds that there is an association relationship between any two entities;
an adding module 326, configured to add the knowledge triple constructed by the constructing module 322 and the association relationship existing between any two entities acquired by the acquiring module 325 to the ontology information.
Further, as shown in fig. 7, the extracting unit 32 further includes:
a processing module 327, configured to process an entity included in the knowledge element information by using entity disambiguation after analyzing the knowledge element information included in the historical budget data;
the processing module 327 is further configured to process the entity included in the knowledge element information by using coreference resolution.
Further, as shown in fig. 7, the extracting unit 32 further includes:
a determining module 328, configured to determine whether a similarity between two triples reaches a preset threshold by calculating word similarity after a knowledge triplet is constructed according to the knowledge element information;
the processing module 327 is further configured to perform deduplication processing on the two triples when the determining module 328 determines whether the similarity between the two triples reaches a preset threshold.
Further, as an implementation of the method shown in fig. 5, an embodiment of the present invention provides an application apparatus for budget management knowledge base. The embodiment of the apparatus corresponds to the embodiment of the method, and for convenience of reading, details in the embodiment of the apparatus are not repeated one by one, but it should be clear that the apparatus in the embodiment can correspondingly implement all the contents in the embodiment of the method. The apparatus is applied to optimize budget management by using knowledge graph, and specifically as shown in fig. 8, the apparatus includes:
a retrieval unit 41, configured to take the budget management knowledge graph as a bottom-level retrieval support when receiving a triggered retrieval instruction;
an output unit 42, configured to output a search result corresponding to the search instruction;
a comparing unit 43, configured to compare the search result output by the output unit 42 with a white list corresponding to different service scenarios;
the output unit 42 is further configured to output alarm information when the comparison unit 43 determines that the retrieval result does not match the white lists corresponding to different service scenarios.
In summary, the embodiments of the present invention provide a method and an apparatus for constructing a budget management knowledge graph, and an application method and an apparatus thereof, where the embodiments of the present invention construct a budget management knowledge graph including entity categories such as organization categories, budget items categories, asset categories, service categories, and similar categories by using historical budget data, and by retrieving the budget management knowledge graph, the embodiments of the present invention can quickly and comprehensively obtain various financial and service data of a query unit as much as possible, thereby being helpful to provide an efficient implementation manner for planning a budget scheme, and judging authenticity and rationality of budget items or budget targets. Compared with the prior art, the method solves the problem that the budget planning in the existing mode cannot be fully and effectively utilized and the intercommunication information and data are shared, so that a plurality of troubles are brought. In addition, the embodiment of the invention also provides a method for verifying the retrieval information by utilizing the white lists corresponding to different service scenes, thereby indirectly performing verification or quality inspection on the existing budgeting.
The budget management knowledge graph constructing device comprises a processor and a memory, wherein the acquiring unit, the extracting unit, the constructing unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more, budget management is optimized by using the knowledge graph through adjusting kernel parameters, and various financial and business data of a query unit can be rapidly and comprehensively acquired as much as possible through retrieving the budget management knowledge graph, so that an efficient implementation mode is provided for the planning of a budget scheme and the judgment of the authenticity and the reasonability of budget items or budget targets.
The application device of the budget management knowledge graph comprises a processor and a memory, wherein the retrieval unit, the output unit, the comparison unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more, and retrieval application is realized by utilizing the knowledge graph through adjusting kernel parameters, so that budget management is optimized.
An embodiment of the present invention provides a storage medium on which a program is stored, where the program implements a method for constructing the budget management knowledge-graph when executed by a processor, or implements a method for applying the budget management knowledge-graph when executed by a processor.
The embodiment of the invention provides a processor, which is used for running a program, wherein the program executes a construction method of the budget management knowledge graph during running, or the program realizes an application method of the budget management knowledge graph when being executed by the processor.
An embodiment of the present invention provides an electronic device 50, as shown in fig. 9, the device includes at least one processor 501, at least one memory 502 connected to the processor 501, and a bus 503; the processor 501 and the memory 502 complete communication with each other through the bus 503; the processor 501 is configured to call program instructions in the memory 502 to execute the above-mentioned construction method of the budget management knowledge-graph or to execute the above-mentioned application method of the budget management knowledge-graph.
The device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:
a method of constructing a budget management knowledge graph, the method comprising: acquiring historical budget data; extracting ontology information from the historical budget data, wherein the ontology information at least comprises: a plurality of entity categories and associated relationships existing between entities respectively corresponding to different entity categories, wherein the entity categories are at least: organization class, budget items class, asset class, service class, contract class; and constructing a budget management knowledge graph according to the association relationship existing between the entities respectively corresponding to the different entity types.
Further, the extracting ontology information from the historical budget data includes: analyzing knowledge element information contained in the historical budget data, wherein the knowledge element information comprises entities, relations among the entities, attributes of the entities and attribute values of the attributes; constructing a knowledge triple according to the knowledge element information; classifying the plurality of entities according to a preset classification rule to obtain an entity corresponding to each category; searching whether any two entities have an association relation between different categories; if so, acquiring the association relation; and adding the association relation between the knowledge triple and the found any two entities into the body information.
Further, after the parsing knowledge element information contained in the historical budget data, the method further includes: processing the entity contained in the knowledge element information by utilizing entity disambiguation; and/or processing the entity contained in the knowledge element information by utilizing coreference resolution.
Further, after the constructing a knowledge triple according to the knowledge element information, the method further includes: judging whether the similarity between the two triples reaches a preset threshold value or not by calculating word similarity; and if so, executing deduplication processing on the two triples.
And, an application method of a budget management knowledge graph, the method comprising: when a triggered retrieval instruction is received, the budget management knowledge graph is used as a bottom retrieval support, and a retrieval result corresponding to the retrieval instruction is output; comparing the retrieval result with a white list corresponding to different service scenes; and if the data are not matched, outputting alarm information.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a device includes one or more processors (CPUs), memory, and a bus. The device may also include input/output interfaces, network interfaces, and the like.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A method for constructing a budget management knowledge graph, the method comprising:
acquiring historical budget data;
extracting ontology information from the historical budget data, wherein the ontology information at least comprises: a plurality of entity categories and associated relationships existing between entities respectively corresponding to different entity categories, wherein the entity categories are at least: organization class, budget items class, asset class, service class, contract class;
and constructing a budget management knowledge graph according to the association relationship existing between the entities respectively corresponding to the different entity types.
2. The method of claim 1, wherein the extracting ontology information from the historical budget data comprises:
analyzing knowledge element information contained in the historical budget data, wherein the knowledge element information comprises entities, relations among the entities, attributes of the entities and attribute values of the attributes;
constructing a knowledge triple according to the knowledge element information;
classifying the plurality of entities according to a preset classification rule to obtain an entity corresponding to each category;
searching whether any two entities have an association relation between different categories;
if so, acquiring the association relation;
and adding the association relation between the knowledge triple and the found any two entities into the body information.
3. The method of claim 2, wherein after said parsing knowledge element information contained in said historical budget data, said method further comprises:
processing the entity contained in the knowledge element information by utilizing entity disambiguation; and/or the presence of a gas in the gas,
and processing the entity contained in the knowledge element information by utilizing coreference resolution.
4. The method of claim 2, wherein after said constructing a knowledge triplet based on said knowledge element information, said method further comprises:
judging whether the similarity between the two triples reaches a preset threshold value or not by calculating word similarity;
and if so, executing deduplication processing on the two triples.
5. A method for applying a budget management knowledge graph, which is used for the budget management knowledge graph obtained by the method for constructing a budget management knowledge graph according to any one of claims 1 to 4, wherein the method comprises:
when a triggered retrieval instruction is received, the budget management knowledge graph is used as a bottom retrieval support, and a retrieval result corresponding to the retrieval instruction is output;
comparing the retrieval result with a white list corresponding to different service scenes;
and if the data are not matched, outputting alarm information.
6. An apparatus for constructing a budget management knowledge graph, the apparatus comprising:
the acquisition unit is used for acquiring historical budget data;
an extracting unit, configured to extract ontology information from the historical budget data acquired by the acquiring unit, where the ontology information at least includes: a plurality of entity categories and associated relationships existing between entities respectively corresponding to different entity categories, wherein the entity categories are at least: organization class, budget items class, asset class, service class, contract class;
and the construction unit is used for constructing the budget management knowledge graph according to the association relation existing between the entities which are extracted by the extraction unit and respectively correspond to different entity types.
7. The apparatus of claim 6, wherein the extraction unit comprises:
the analysis module is used for analyzing knowledge element information contained in the historical budget data, wherein the knowledge element information contains entities, relations among the entities, attributes of the entities and attribute values of the attributes;
the construction module is used for constructing a knowledge triple according to the knowledge element information obtained by the analysis module;
the classification module is used for classifying the entities obtained by the analysis modules according to a preset classification rule to obtain an entity corresponding to each category;
the searching module is used for searching whether any two entities have an association relation between different categories;
the obtaining module is used for obtaining the incidence relation if the searching module finds that any two entities have the incidence relation;
and the adding module is used for adding the knowledge triple constructed by the constructing module and the incidence relation of any two entities acquired by the acquiring module into the body information.
8. An apparatus for applying a budget management knowledge graph, the apparatus comprising:
the retrieval unit is used for taking the budget management knowledge graph as bottom retrieval support when receiving a triggered retrieval instruction;
the output unit is used for outputting a retrieval result corresponding to the retrieval instruction;
the comparison unit is used for comparing the retrieval result output by the output unit with the white lists corresponding to different service scenes;
and the output unit is also used for outputting alarm information when the comparison unit determines that the retrieval result is not matched with the white lists corresponding to different service scenes.
9. A storage medium, characterized in that the storage medium comprises a stored program, wherein when the program runs, the apparatus on which the storage medium is located is controlled to execute the budget management knowledge graph construction method according to any one of claims 1 to 4;
alternatively, the method of applying a budget management knowledge graph according to claim 5 is performed.
10. An electronic device, comprising at least one processor, and at least one memory, bus connected to the processor;
the processor and the memory complete mutual communication through the bus;
the processor is configured to invoke program instructions in the memory to perform the method of construction of a budget management knowledge-graph according to any one of claims 1 to 4;
alternatively, the method of applying a budget management knowledge graph according to claim 5 is performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910993811.9A CN112699245A (en) | 2019-10-18 | 2019-10-18 | Construction method and device and application method and device of budget management knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910993811.9A CN112699245A (en) | 2019-10-18 | 2019-10-18 | Construction method and device and application method and device of budget management knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112699245A true CN112699245A (en) | 2021-04-23 |
Family
ID=75504645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910993811.9A Pending CN112699245A (en) | 2019-10-18 | 2019-10-18 | Construction method and device and application method and device of budget management knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112699245A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114840686A (en) * | 2022-05-07 | 2022-08-02 | 中国电信股份有限公司 | Knowledge graph construction method, device and equipment based on metadata and storage medium |
| CN115391545A (en) * | 2022-04-26 | 2022-11-25 | 航天宏图信息技术股份有限公司 | Knowledge graph construction method and device for multi-platform collaborative observation task |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108932340A (en) * | 2018-07-13 | 2018-12-04 | 华融融通（北京）科技有限公司 | The construction method of financial knowledge mapping under a kind of non-performing asset operation field |
| CN109597855A (en) * | 2018-11-29 | 2019-04-09 | 北京邮电大学 | Domain knowledge map construction method and system based on big data driving |
| EP3550464A1 (en) * | 2018-04-05 | 2019-10-09 | Accenture Global Solutions Limited | Data security and protection system using distributed ledgers to store validated data in a knowledge graph |
-
2019
- 2019-10-18 CN CN201910993811.9A patent/CN112699245A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3550464A1 (en) * | 2018-04-05 | 2019-10-09 | Accenture Global Solutions Limited | Data security and protection system using distributed ledgers to store validated data in a knowledge graph |
| CN108932340A (en) * | 2018-07-13 | 2018-12-04 | 华融融通（北京）科技有限公司 | The construction method of financial knowledge mapping under a kind of non-performing asset operation field |
| CN109597855A (en) * | 2018-11-29 | 2019-04-09 | 北京邮电大学 | Domain knowledge map construction method and system based on big data driving |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115391545A (en) * | 2022-04-26 | 2022-11-25 | 航天宏图信息技术股份有限公司 | Knowledge graph construction method and device for multi-platform collaborative observation task |
| CN114840686A (en) * | 2022-05-07 | 2022-08-02 | 中国电信股份有限公司 | Knowledge graph construction method, device and equipment based on metadata and storage medium |
| CN114840686B (en) * | 2022-05-07 | 2024-01-02 | 中国电信股份有限公司 | Knowledge graph construction method, device, equipment and storage medium based on metadata |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10977293B2 (en) | Technology incident management platform | |
| CN108089843B (en) | Intelligent bank enterprise-level demand management system | |
| US9990356B2 (en) | Device and method for analyzing reputation for objects by data mining | |
| CN110569369A (en) | Generation method and device, application method and device of knowledge graph of bank financial system | |
| CN106067094A (en) | A kind of dynamic assessment method and system | |
| CN113157947A (en) | Knowledge graph construction method, tool, device and server | |
| CN111538794A (en) | Data fusion method, device and equipment | |
| CN112927082A (en) | Credit risk prediction method, apparatus, device, medium, and program product | |
| CN116402512B (en) | Account security check management method based on artificial intelligence | |
| CN111553556A (en) | Business data analysis method and device, computer equipment and storage medium | |
| CN113360676A (en) | Method and device for determining potential relation of enterprise based on knowledge graph | |
| CN113538154A (en) | Risk object identification method and device, storage medium and electronic equipment | |
| CN112966162A (en) | Scientific and technological resource integration method and device based on data warehouse and middleware | |
| CN112699245A (en) | Construction method and device and application method and device of budget management knowledge graph | |
| CN113220885B (en) | Text processing method and system | |
| CN112907358A (en) | Loan user credit scoring method, loan user credit scoring device, computer equipment and storage medium | |
| KR102244887B1 (en) | Method and system for recommending SQL query | |
| CN116881395A (en) | Public opinion information detection method and device | |
| CN111177653A (en) | Credit assessment method and device | |
| CN110941952A (en) | Method and device for perfecting audit analysis model | |
| CN115934693A (en) | Dynamic calculation method for regional real population | |
| CN115239214A (en) | Enterprise evaluation processing method and device and electronic equipment | |
| KR20230103025A (en) | Method, Apparatus, and System for provision of corporate credit analysis and rating information | |
| Dahiya et al. | Effective data warehouse for information delivery: a literature survey and classification | |
| JP2017010376A (en) | Mart-less verification support system and mart-less verification support method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |